The evolving landscapes of user modelling, adaptation, and personalisation necessitate a nuanced exploration of context and its impact on human-computer interaction. This evolution represents a paradigm shift towards placing the user at the centre of context representation, acknowledging the multifaceted nature of context as it intertwines with user needs, environmental changes, and technological advancements.
The second edition of the Context Representation in User Modeling (CRUM) workshop, themed "Human-Centric Context", seeks to foster a comprehensive understanding of context by focusing on the dynamic interplay between subjective and objective contexts in enhancing user experience. We welcome submissions that explore the nuances of human-centric context across various domains, aiming to standardise context modelling practices that enhance user engagement, privacy, and trust in multi-stakeholder environments.
The goal of CRUM 2024 is to consolidate the various ways in which context is stored, retrieved, used, analysed, and interpreted by academicians, researchers, and users of a variety of user-facing systems. In that vein, we introduce the theme of this workshop: Representation of Human-Centric Context. "Human-centric context" can be defined as understanding and accounting for the dynamic interaction between the user model and the contextual environment. Such a paradigm shift aims to redefine the contextual landscape, a dynamic and multifaceted environment where contextual elements – ranging from physical settings over social dynamics to technological interfaces – interact and influence user experiences and behaviour. This landscape evolves with user needs, environmental changes, and technological advancements, representing the intricate web of variables that define human-computer interactions and user modelling. CRUM 2024 will explore the subjectivity of contextual information in anthropocentric technologies across various domains.
Evolving from last year's workshop, CRUM 2024 invites multiple submission types. We welcome long papers (up to 7 pages) and provocation/opinion papers (up to 2 pages). Details on the content expectation for both submission types are provided below.
Topics considered relevant to the theme of this workshop include, but are not limited to:
Additionally, topics considered relevant to the theme of this workshop include, but are not limited to:
Camera Ready Deadline
CRUM 2024 accepts long papers (up to 7 pages excluding references and appendices).
In line with UMAP 2024's content expectation, papers should aim to report on original contributions in the field of the understanding and representation of context as well as the use of contextual information within the framework of user modeling, adaptive agents, personalization, and intelligent systems. Papers showcasing innovation within explainability and vulnerability analysis in agents which process and use contextual information are welcome.
Evaluations of proposed applications must be commensurate with the claims made in the paper. Depending on the intended contribution, this may include simulation stidies, offline evaluation, A/B tests, controlled user experiments, or human evalution, which is subject to ACM guidelines involving human participants.
Research procedures and technical methods should be presented in sufficient detail to ensure scrutiny and reproducibility. We recognize that user data may be proprietary or confidential, but we encourage the sharing of (anonymized, cleaned) data sets, data collection procedures, and code. Results should be clearly communicated and implications of the contributions/findings for UMAP and beyond should be explicitly discussed.
CRUM 2024 accepts provocation/opinion papers (up to 2 pages excluding references and appendices).
Provocation and opinion papers are meant to challenge the status quo and present novel, radical, or alternative methods of understanding and representing context as well as the use of contextual information within the framework of user modeling, adaptive agents, personalization, and intelligent systems. Papers showcasing innovation within explainability and vulnerability analysis in agents which process and use contextual information are welcome.
Authors are asked to provide a clear and concise argument for their position and claims alongwith preliminary evidentiary support, if possible. Authors are also encouraged to provide an analysis of the implications of their position for UMAP and beyond. Provocation pieces should consider aspects of viability, desirability, and feasibility of the proposed ideas.
Challenges and limitations of the proposed ideas should also be discussed in sufficient detail. We encourage new perspectives and analyses of existing limitations within the field, as well as the identification of novel challenges. Additionally, thought-provoking alternative viewpoints and perspectives on the future of human-centric context are also welcome.
All submissions to the workshop should use the same ACM template (single-column format) and formatting adopted by the main UMAP conference. The templates and instructions are available here.
We encourage authors to submit works in progress, negative results, insights, position papers, as well as case studies on context and its role in user modeling and adaptive systems.
CRUM follows a rigorous double-blind peer review policy. Please ensure that all workshop submissions are anonymized.
CRUM 2024 has no dual submission policy, and works previously published elsewhere should not be submitted. Submitted manuscripts should also not currently be under review at another publication venue. ACM's publication policy is detailed below:
We are increasingly developing sophisticated systems which are aware of the context that they are used in, and intelligently adapt their behavior to this context. This keynote delves into the essence of 'context', acknowledging its diverse conceptualizations in literature, ranging from 'any information' to a few categories. Despite acknowledging that the relevance of context is domain-specific, it often remains unclear what is relevant specifically.
Technically, context representations aim to objectively capture measurable context elements. However, practical significance often lies at a different abstraction level, where a context element's relevance and meaning may shift based on how other context elements manifest. For instance, spacial coordinates have no immediate connection with the real word; their relevance and meaning are defined by what is there else. An individual's (past) experience further complicates relevance: Is it an arbitrary house or is the one where you grew up? Do you currently live there? It context could become more intricate if a stranger enters that house.
In this keynote address, I will embrace the subtleties of context, emphasizing that the compound of context elements matters, and underscoring that objective context representations may often only serve as proxies for truly significant experienced context.
Christine Bauer is EXDIGIT Professor of Interactive Intelligent Systems at the Department of Artificial Intelligence and Human Interfaces (AIHI) at the Paris Lodron University Salzburg, Austria.
Her research centers on interactive intelligent systems, where she integrates research on intelligent technologies, the interaction of humans with intelligent systems, and their interplay. Central themes in her research are context and context-adaptivity. In recent years, she worked on context-aware recommender systems in the music and media domains. The core interests in her research activities are fairness and multi-method evaluations. She has authored more than 100 papers and holds several best paper awards and many awards for her reviewing activities. She is on the Editorial Boards of ACM Transactions on Recommender Systems (TORS) and ACM Transactions on Information Systems (TOIS). Further, she is co-organizer of the Workshop series "Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES)" at RecSys 2021-2023. Further information can be found here.
Judy Kay is Professor of Computer Science. She leads the Human Centred Technology Research Cluster, in the Faculty of Engineering at the University of Sydney.
A core focus of her research has been to create infrastructures and interfaces for personalisation so that people can scrutinise and control them. She has created such systems to support people in lifelong, life-wide learning. This ranges from formal education settings to supporting people in using their long-term ubicomp data to support self-monitoring, reflection and planning and includes medical contexts such as learning communication skills in medical settings. She has integrated this into new forms of interaction including virtual reality, surface computing, wearables and ambient displays. Her research has been commercialised and deployed and she has extensive publications in leading venues for research in user modelling, AIED, human computer interaction and ubicomp. She has held leadership roles in top conferences in these areas and is Editor-in-Chief of the IJAIED, International Journal of Artificial Intelligence in Education (IJAIED), recent Editor and now Advisory Board member of IMWUT, Interactive Mobile Wearable and Ubiquitous Technology (IMWUT) and Advisory Board member of ACM Transactions on Interactive Intelligent Systems TiiS).
Trinity College Dublin
Trinity College Dublin
Trinity College Dublin